In a high saturated market where a variety of MNOs (Mobile Network Operators) oer relatively homogeneous wireless technologies and services in the same area or region, customers have the freedom to choose the service based on any factor they deem important. In addition to this, mobile number portability contributes to a phenomenon called churning where customers migrate from one Mobile Network Operator (MNO) to another. Churning impacts not only the network design but also the pricing methods adopted by MNOs and, and hence their revenue. It is because of this that MNOs try to reduce churn through retention campaigns detecting potential churners before they leave the service. The mainstream approach to churn prediction considers each customer individually. Preliminary studies have shown that members in the social circle of a subscriber also inuence the subscriber to churn. Thus, systems that take social aspects into account poses an emerging theoretical challenge with potentially great practical implications. The state of the art has focused on proposing methods to identify churners based on data mining techniques, however these techniques doesn't always oer clear explanations for churn reasons. Instead, we use a technique called Agent-Based Modeling to model customers in the mobile telecommunication market and assess the eects of customers characteristics and behaviors on such market. We propose a model that includes some relevant demographic and psychographic characteristics and the utilizations of usage proles to describe customers individually. We propose to take into account social behavior. We modied an existing social network generator algorithm to take into account the user proles when creating a connection. We show through experimentation that using our approach, compared to not using social networks or homophily, yields better results.
This letter proposes a novel and open method for pricing substitute elastic services in a streaming content delivery scenario when their Grade of Service (GoS) is guaranteed. The method forces each Service Provider (SP) to calculate the rate for each substitute service that guarantees the GoS. The price of each service is obtained according to the maximization of a chosen revenue function and the estimation of its demand function. This letter illustrates the method calculating the price of two substitute services with a selected exponential demand function, where the assignation of the prices depend on the maximization of a selected revenue function.Postprint (published version
Mobile Network Operators (MNOs) present wireless services of the same kind in identical zones, clients select the service taking into account any element they consider relevant. Churning hits on the design of the network and the method to assign prices by MNOs, and of course their earnings. Therefore, MNOs try to reduce churn detecting potential churners before they leave the service. Our approach to churn prediction considers each customer individually. Previous research shows that members of the social circle of a subscriber may influence churn. Thus, many scenarios that describe social relations, and in which churning processes could be expected, set an emerging challenge with practical implications. This paper uses the Agent-Based Modelling (ABM) technique to model customers. The model’s parameters include demographic and psychographic features as well as usage profiles according to their social behavior considering their customers’ profiles. Our model modifies and extends an existing real social network generator algorithm that considers customer’s profiles and homophily considerations to create connections. We show that using our approach, groups of customers with greater tendency to churn due to the influence of their social networks can be identified better.Peer ReviewedPostprint (author's final draft
This paper presents an alternative calculation procedure to calculate the mortality rate, exploiting the data available in the Eurostat demography database for Spain. This methodology has been devised based on two of the most widely known and widespread models to establish the mortality rate: The Gompertz-Makeham (GM) and Lee-Carter (LC) models. Our main goal is to obtain a model yielding a similar accuracy than LC or GM, but able to capture the variation of their parameters over time and ages. The method proposed herewith works by applying simple or double fitting, with non-linear functions, to the values of the parameters considered by each one of such models. One of the main advantages of our approach is that we considerably reduce the amount of data that is required to establish the mortality rate, with respect to what would be needed if the traditional models were used. On the other hand, it also allows analyzing the evolution of the mortality rate, even if no real data was available for a particular year. The results evince that, besides fulfilling the two aforementioned goals, the proposed scheme yields an estimation error that is comparable with that offered by the traditional approach.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.